A sentence-level visualization tool for attention in large language models
Project description
SAVIS: Sentence-Level Attention Visualization for Large Language Models
SAVIS (Sentence-level Attention VISualization) is a Python library for visualizing inter-sentence attention in large language models (LLMs), specifically designed for public relations (PR) analysis. This tool enhances the interpretability of LLMs by providing an intuitive visualization of how attention is distributed across sentences in generated text.
Features
- Inter-sentence attention calculation
- Interactive visualization of attention patterns
- Support for various LLMs through Hugging Face's
transformers
library - Customizable for PR-specific analysis tasks with Jupyter Notebook
Installation
pip install savis
Quick Start
from savis import TextGenerator, ISA, ISAVisualization
# Initialize the text generator with your chosen model
generator = TextGenerator("Model name")
# Generate text and get attention data
input_text = "Your input prompt here"
generated_text, attentions, tokenizer, input_ids, outputs = generator.generate_text(input_text)
# Calculate inter-sentence attention
isa = ISA(outputs.sequences[0], attentions, tokenizer)
# Visualize the attention patterns
vis = ISAVisualization(isa.sentence_attention, isa.sentences)
vis.visualize_sentence_attention()
Key Components
TextGenerator
: Interfaces with the LLM to generate text and extract attention information.Attention
: Manages the underlying LLM and provides methods for obtaining attention data from the model.ISA
(Inter-Sentence Attention): Processes raw attention data to compute attention between sentences.ISAVisualization
: Creates interactive visualizations of the computed inter-sentence attention.
These components work together to provide a comprehensive pipeline from text generation to attention visualization:
TextGenerator
uses the LLM to generate text based on input prompts.Attention
handles the interaction with the LLM, extracting detailed attention information.ISA
takes the raw attention data and computes meaningful inter-sentence attention scores.ISAVisualization
takes these scores and creates interactive visualizations.
License
SAVIS is released under the MIT License. See the LICENSE file for more details.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file savis-0.3.6.tar.gz
.
File metadata
- Download URL: savis-0.3.6.tar.gz
- Upload date:
- Size: 4.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c6ddf048e44ece6242c583754a6363a6f8d5c4c386ffc5430edcd2f276c4036b |
|
MD5 | 5028c049630859313f45d31cd6f199ec |
|
BLAKE2b-256 | af7f0c504362bc4dfacf459455d0b998689a1700119d32952397d23593c73e60 |
File details
Details for the file savis-0.3.6-py3-none-any.whl
.
File metadata
- Download URL: savis-0.3.6-py3-none-any.whl
- Upload date:
- Size: 9.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6f1dfc160779e329a61aae394eadc07bc94c2bf2856ca8b2cedcefce0ef505f1 |
|
MD5 | 005218c4743fe81a633f708173132f79 |
|
BLAKE2b-256 | cffd084ce7898f5191442f0b8499e278b3caf8cd2cfa247e67cefb8a7ffe148c |